asana
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation provides multiple examples of Python scripts that the agent can execute to interact with the API. These scripts use the shell's heredoc pattern to pass Python code to the interpreter for handling network requests and connection management.\n- [PROMPT_INJECTION]: The skill is designed to fetch and process data from the external Asana API, which represents an indirect prompt injection surface. While no malicious activity was found, data from such APIs should be treated as untrusted.\n
- Ingestion points: Data is retrieved from various Asana endpoints (tasks, projects, workspaces) as described in SKILL.md.\n
- Boundary markers: None are specified in the instructional examples for separating API data from prompt instructions.\n
- Capability inventory: The skill utilizes network capabilities through standard libraries (urllib and requests) and demonstrates shell execution capability via provided script examples.\n
- Sanitization: No sanitization or data validation steps are mentioned or demonstrated for the content retrieved from the external API.
Audit Metadata